© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130700
    Prev
    Next
    INDEX
    Explanations

    both / respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.46
     or
    -1.23
     for
    -0.96
     is
    -0.92
    眼光
    -0.89
     West
    -0.89
     at
    -0.88
     D
    -0.88
     '/';
    -0.86
     a
    -0.84
    POSITIVE LOGITS
    それぞれ
    1.85
    respectively
    1.52
    Both
    1.49
     jeweils
    1.46
     respectively
    1.45
    どちらも
    1.45
    分别
    1.41
     both
    1.38
     masing
    1.38
     each
    1.34
    Activations Density 0.026%

    No Known Activations